R Notebook

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.1 ──
✔ ggplot2 3.3.6     ✔ purrr   0.3.4
✔ tibble  3.1.7     ✔ dplyr   1.0.9
✔ tidyr   1.2.0     ✔ stringr 1.4.0
✔ readr   2.1.2     ✔ forcats 0.5.1
── Conflicts ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

library(janitor)

Attaching package: ‘janitor’

The following objects are masked from ‘package:stats’:

    chisq.test, fisher.test

library(CodeClanData)

Attaching package: ‘CodeClanData’

The following object is masked from ‘package:dplyr’:

    starwars

The following object is masked from ‘package:tidyr’:

    population

library(fmsb)

whisky <- CodeClanData::whisky %>% clean_names()

whisky %>% 
  distinct(distillery)

whisky %>% 
  distinct(region)

whisky %>% 
  distinct(owner)

whisky %>% 
  distinct(floral)

whisky <- whisky %>% 
  mutate(across(body:floral, as.numeric))

whisky <- whisky %>% 
  pivot_longer(cols = body:floral,
               names_to = "notes",
               values_to = "score")

whisky %>%
  filter(distillery == "Aberfeldy") %>% 
  ggplot(aes(x = notes,
             y = score,
             fill = region)) +
  geom_col() +
  scale_y_continuous(expand = c(0, 0)) +
  scale_y_continuous(limits = c(0, 4)) +
  theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, size = 14),
        axis.text.y = element_text(size = 14),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20),
        legend.title = element_text(size = 20),
        legend.text = element_text(size = 14)) +
  labs(x = "Notes",
       y = "\nScore",
       fill = "Whisky Region")

Scale for 'y' is already present. Adding another scale for 'y', which will replace the existing scale.

all_regions <- unique(whisky$region)

all_distilleries <- unique(whisky$distillery)

p <- whisky %>%
  group_by(owner) %>% 
  mutate(count = n()/12) %>% 
  ungroup() %>% 
  filter(count > 1) %>%
  filter(year_found > 1810 & year_found < 1840) %>% 
  ggplot(aes(x = year_found,
             y = capacity,
             colour = owner)) +
  geom_point(aes(shape = region)) +
        theme(axis.text.x = element_text(size = 8),
            axis.text.y = element_text(size = 8),
            axis.title.x = element_text(size = 8),
            axis.title.y = element_text(size = 8),
            legend.title = element_text(size = 8),
            legend.text = element_text(size = 8),
            plot.title = element_text(size = 8)) +
  scale_y_continuous(labels = scales::comma) +
      labs(x = "Year Founded",
           y = "Capacity",
           colour = "Distillery Owner",
           title = "Distillery Capacity by Year Founed\n")

plotly::ggplotly(p)

whisky %>% 
  group_by(year_found) %>% 
  summarise(count = n()) %>% 
  arrange(desc(count))